Multiple machine learning, molecular docking, and ADMET screening approach for identification of selective inhibitors of CYP1B1

Pharmacophore-based virtual screening, molecular docking and molecular dynamics studies for the discovery of novel neuraminidase inhibitors

The in silico evaluation of 27 p-aminosalicylic acid derivatives, also referred to as neuraminidase inhibitors was the focus of the current study. To search and predict new potential neuraminidase inhibitors, this study was based on the ligand-based pharmacophore modeling, 3D QSAR, molecular docking, ADMET and MD simulation studies. The data was generated from recently reported inhibitors and divided into two groups, one of these group has 17 compounds for training and the second group has 10 compounds for testing purpose. The generated pharmacophore has known as ADDPR_4 was found statistically significant 3D-QSAR model owing the high trust scores (R2 = 0.974, Q2 = 0.905, RMSE = 0.23). Morever external validation was also employed to evaluate the prediction capacity of the built pharmacophore model (R2pred = 0.905). In addition, in silico ADMET, analyses were employed to evaluate the obtained hits for drug likeness properties. The stability of formed complexes was further evaluated using molecular dynamics. Top two hits showed stable complexes with Neuraminidase based on calculated total binding energy by MM-PBSA.Communicated by Ramaswamy H. Sarma.

Genetic Signatures for Distinguishing Chemo-Sensitive from Chemo-Resistant Responders in Prostate Cancer Patients

Prostate cancer remains a significant public health concern in sub-Saharan Africa, particularly impacting South Africa with high mortality rates. Despite many years of extensive research and significant financial expenditure, there has yet to be a definitive solution to prostate cancer. It is not just individuals who vary in their response to treatment, but even different nodules within the same tumor exhibit unique transcriptome patterns. These distinctions extend beyond mere differences in gene expression levels to encompass the control and networking of individual genes. Escalating chemotherapy resistance in prostate cancer patients has prompted increased research into its underlying mechanisms. The heterogeneous nature of transcriptomic organization among men makes the pursuit of universal biomarkers and one-size-fits-all treatments impractical. This study delves into the expression of drug resistance-associated genes, ABCB1 and CYP1B1, in cancer cells. Employing bioinformatics, we explored the molecular pathways and cascades linked to drug resistance following upregulation of these genes. Samples were obtained from archived prostate cancer patient specimens through pre-treatment biopsies of two categories: good vs. poor responders, with cDNAs synthesized from isolated RNAs subjected to qPCR analysis. The results revealed increased ABCB1 and CYP1B1 expression in tumor samples of the poor responders. Gene enrichment and network analysis associated ABCB1 with ABC transporters and LncRNA-mediated therapeutic resistance (WP3672), while CYP1B1 was linked to ovarian steroidogenesis, tryptophan metabolism, steroid hormone biosynthesis, benzo(a)pyrene metabolism, the sulindac metabolic pathway, and the estrogen receptor pathway, which are associated with drug resistance. Both ABCB1 and CYP1B1 correlated with microRNAs in cancer and the Nuclear Receptors Meta-Pathway. STRING analysis predicted protein-protein interactions of ABCB1 and CYP1B1 with Glutathione S-transferase Pi, Catechol O-methyltransferase, UDP-glucuronosyltransferase 1-6, Leucine-rich Transmembrane and O-methyltransferase (LRTOMT), and Epoxide hydrolase 1, with scores of 0.973, 0.971, 0.966, 0.966, and 0.966, respectively. Furthermore, molecular docking analysis of the chemotherapy drug, docetaxel, with CYP1B1 and ABCB1 revealed robust molecular interactions, with binding energies of -20.37 and -15.25 Kcal/mol, respectively. These findings underscore the susceptibility of cancer patients to drug resistance due to increased ABCB1 and CYP1B1 expression in tumor samples from patients in the poor-responders category that affects associated molecular pathways. The potent molecular interactions of ABCB1 and CYP1B1 with docetaxel further emphasize the potential basis for chemotherapy resistance.

Scaffold hopping for designing of potent and selective CYP1B1 inhibitors to overcome docetaxel resistance: synthesis and evaluation

Cytochrome P450 1B1, a tumor-specific overexpressed enzyme, significantly impairs the pharmacokinetics of several commonly used anticancer drugs including docetaxel, paclitaxel and cisplatin, leading to the problem of resistance to these drugs. Currently, there is no CYP1B1 inhibition-based adjuvant therapy available to treat this resistance problem. Hence, in the current study, exhaustive in-silico studies including scaffold hopping followed by molecular docking, three-dimensional quantitative structure-activity relationships (3D-QSAR), molecular dynamics and free energy perturbation studies were carried out to identify potent and selective CYP1B1 inhibitors. Initially, scaffold hopping analysis was performed against a well-reported potent and selective CYP1B1 inhibitor (i.e. compound 3n). A total of 200 scaffolds were identified along with their shape and field similarity scores. The top three scaffolds were further selected on the basis of these scores and their synthesis feasibility to design some potent and selective CYP1B1 inhibitors using the aforementioned in-silico techniques. Designed molecules were further synthesized to evaluate their CYP1B1 inhibitory activity and docetaxel resistance reversal potential against CYP1B1 overexpressed drug resistance MCF-7 cell line. In-vitro results indicated that compounds 2a, 2c and 2d manifested IC50 values for CYP1B1 ranging from 0.075, 0.092 to 0.088 μM with at least 10-fold selectivity. At low micromolar concentrations, compounds 1e, 1f, 2a and 2d exhibited promising cytotoxic effects in the docetaxel-resistant CYP1B1 overexpressed MCF-7 cell line. In particular, compound 2a is most effective in reversing the resistance with IC50 of 29.0 ± 3.6 μM. All of these discoveries could pave the way for the development of adjuvant therapy capable of overcoming CYP1B1-mediated resistance.Communicated by Ramaswamy H. Sarma.

3D-QSAR assisted identification of selective CYP1B1 inhibitors: an effective bioisosteric replacement/molecular docking/electrostatic complementarity analysis

Cytochrome P450-1B1 is a majorly overexpressed drug-metabolizing enzyme in tumors and is responsible for inactivation and subsequent resistance to a variety of anti-cancer drugs, i.e., docetaxel, tamoxifen, and cisplatin. In the present study, a 3D quantitative structure-activity relationship (3D-QSAR) model has been constructed for the identification, design, and optimization of novel CYP1B1 inhibitors. The model has been built using a set of 148 selective CYP1B1 inhibitors. The developed model was evaluated based on certain statistical parameters including q2 and r2 which showed the acceptable predictive and descriptive capability of the generated model. The developed 3D-QSAR model assisted in understanding the key molecular fields which were firmly related to the selective CYP1B1 inhibition. A theoretic approach for the generation of new lead compounds with optimized CYP1B1 receptor affinity has been performed utilizing bioisosteric replacement analysis. These generated molecules were subjected to a developed 3D-QSAR model to predict the inhibitory activity potentials. Furthermore, these compounds were scrutinized through the activity atlas model, molecular docking, electrostatic complementarity, molecular dynamics, and waterswap analysis. The final hits might act as selective CYP1B1 inhibitors which could address the issue of resistance. This 3D-QSAR includes several chemically diverse selective CYP1B1 receptor ligands and well accounts for the individual ligand's inhibition affinities. These features of the developed 3D-QSAR model will ensure future prospective applications of the model to speed up the identification of new potent and selective CYP1B1 receptor ligands.

Artificial Intelligence in Drug Metabolism and Excretion Prediction: Recent Advances, Challenges, and Future Perspectives

Drug metabolism and excretion play crucial roles in determining the efficacy and safety of drug candidates, and predicting these processes is an essential part of drug discovery and development. In recent years, artificial intelligence (AI) has emerged as a powerful tool for predicting drug metabolism and excretion, offering the potential to speed up drug development and improve clinical success rates. This review highlights recent advances in AI-based drug metabolism and excretion prediction, including deep learning and machine learning algorithms. We provide a list of public data sources and free prediction tools for the research community. We also discuss the challenges associated with the development of AI models for drug metabolism and excretion prediction and explore future perspectives in the field. We hope this will be a helpful resource for anyone who is researching in silico drug metabolism, excretion, and pharmacokinetic properties.

In silico guided designing of optimized benzochalcones derivatives as potent CYP1B1 inhibitors: An integrated in vitro and ONIOM study

Cytochrome P4501B1 (CYP1B1) is reported to be overexpressed in various malignancies including ovarian, lung, lymph, and breast cancers. The overexpression of this enzyme is accountable for the biotransformation-based inactivation of some anti-cancer drugs i.e. Docetaxel, Paclitaxel, and Cisplatin. To circumvent solutions to this issue, the current study reports some optimized derivatives of benzochalcone as selective CYP1B1 inhibitors. The optimized derivatives were screened using some structure-based drug-designing approaches including molecular docking and molecular dynamics. The implemented approaches revealed that all the designed molecules demonstrated not only essential interactions with key amino acid residues but also maintained stability within the active site of CYP1B1. Furthermore, to validate the in-silico results and develop a SAR, the designed molecules were subsequently synthesized and tested for their ability to selectively inhibit CYP1B1 over CYP1A1 using well established EROD assay. This assay results suggested that compounds 1(c), 1(d), and 1(e) are eightfold more selective CYP1B1 inhibitors over CYP1A1 with IC₅₀ values ranging from 0.06 to 0.09 μM respectively. Among these, compound 1(d) manifested potent inhibitory activity i.e. IC₅₀ of 0.06 μM with 24 folds selectivity over 1A1. To have a better insight into the binding pattern of 1(d) within CYP1B1 and precisely compute binding affinity for 1(d)-CYP1B1 complex, one of the advanced QM/MM approaches i.e. ONIOM has been implemented. Where 1(d)-CYP1B1 complex conferred comparable binding affinity in terms of ΔG (kcal/mol) with that of ANF-CYP1B1 complex. This research could provide a suitable starting point for the development of more potent multi-functional compounds with CYP1B1 inhibitory activity.

Machine learning driven drug repurposing strategy for identification of potential RET inhibitors against non-small cell lung cancer

Non-small cell lung cancer (NSCLC) remains the leading cause of mortality and morbidity worldwide accounting about 85% of total lung cancer cases. The receptor REarranged during Transfection (RET) plays an important role by ligand independent activation of kinase domain resulting in carcinogenesis. Presently, the treatment for RET driven NSCLC is limited to multiple kinase inhibitors. This situation necessitates the discovery of novel and potent RET specific inhibitors. Thus, we employed high throughput screening strategy to repurpose FDA approved compounds from DrugBank comprising of 2509 molecules. It is worth noting that the initial screening is accomplished with the aid of in-house machine learning model built using IC₅₀ values corresponding to 2854 compounds obtained from BindingDB repository. A total of 497 compounds (19%) were predicted as actives by our generated model. Subsequent in silico validation process such as molecular docking, MMGBSA and density function theory analysis resulted in identification of two lead compounds named DB09313 and DB00471. The simulation study highlights the potency of DB00471 (Montelukast) as potential RET inhibitor among the investigated compounds. In the end, the half-minimal inhibitory activity of montelukast was also predicted against RET protein expressing LC-2/ad cell lines demonstrated significant anticancer activity. Collective analysis from our study highlights that montelukast could be a promising candidate for the management of RET specific NSCLC.

Identification of potential extracellular signal-regulated protein kinase 2 inhibitors based on multiple virtual screening strategies

The integration of multiple virtual screening strategies facilitates the balance of computational efficiency and prediction accuracy. In this study, we constructed an efficient and reliable "multi-stage virtual screening-in vitro biological validation" system to identify potential inhibitors targeting extracellular signal-regulated protein kinase 2 (ERK2). Firstly, we rapidly obtained 10 candidate ERK2 inhibitors with desirable pharmacokinetic characteristics from thousands of named natural products in ZINC database based on machine learning classification models and ADME/T prediction. The structure-based molecular docking approach was then used to obtain four further hits with lower binding free energy compared to the positive control molecule Magnolipin. Subsequently, the two compounds were purchased for in vitro biological validation considering commercial availability and economic cost, and the results showed that Dodoviscin A exhibited acceptable inhibitory activity on ERK2 (IC50 = 10.79 μm). Finally, the mechanism of action and binding stability of this natural product inhibitor were investigated by binding mode analysis and molecular dynamics simulation.

Prediction and Screening Model for Products Based on Fusion Regression and XGBoost Classification

Performance prediction based on candidates and screening based on predicted performance value are the core of product development. For example, the performance prediction and screening of equipment components and parts are an important guarantee for the reliability of equipment products. The prediction and screening of drug bioactivity value and performance are the keys to pharmaceutical product development. The main reasons for the failure of pharmaceutical discovery are the low bioactivity of the candidate compounds and the deficiencies in their efficacy and safety, which are related to the absorption, distribution, metabolism, excretion, and toxicity (ADMET) of the compounds. Therefore, it is very necessary to quickly and effectively perform systematic bioactivity value prediction and ADMET property evaluation for candidate compounds in the early stage of drug discovery. In this paper, a data-driven pharmaceutical products screening prediction model is proposed to screen drug candidates with higher bioactivity value and better ADMET properties. First, a quantitative prediction method for bioactivity value is proposed using the fusion regression of LGBM and neural network based on backpropagation (BP-NN). Then, the ADMET properties prediction method is proposed using XGBoost. According to the predicted bioactivity value and ADMET properties, the BVAP method is defined to screen the drug candidates. And the screening model is validated on the dataset of antagonized Erα active compounds, in which the mean square error (MSE) of fusion regression is 1.1496, the XGBoost prediction accuracy of ADMET properties are 94.0% for Caco-2, 95.7% for CYP3A4, 89.4% for HERG, 88.6% for hob, and 96.2% for Mn. Compared with the commonly used methods for ADMET properties such as SVM, RF, KNN, LDA, and NB, the XGBoost in this paper has the highest prediction accuracy and AUC value, which has better guiding significance and can help screen pharmaceutical product candidates with good bioactivity, pharmacokinetic properties, and safety.

Oncological drug discovery: AI meets structure-based computational research

The integration of machine learning and structure-based methods has proven valuable in the past as a way to prioritize targets and compounds in early drug discovery. In oncological research, these methods can be highly beneficial in addressing the diversity of neoplastic diseases portrayed by the different hallmarks of cancer. Here, we review six use case scenarios for integrated computational methods, namely driver prediction, computational mutagenesis, (off)-target prediction, binding site prediction, virtual screening, and allosteric modulation analysis. We address the heterogeneity of integration approaches and individual methods, while acknowledging their current limitations and highlighting their potential to bring drugs for personalized oncological therapies to the market faster.

Natural Product-Based Studies for the Management of Castration-Resistant Prostate Cancer: Computational to Clinical Studies

Background: With prostate cancer being the fifth-greatest cause of cancer mortality in 2020, there is a dire need to expand the available treatment options. Castration-resistant prostate cancer (CRPC) progresses despite androgen depletion therapy. The mechanisms of resistance are yet to be fully discovered. However, it is hypothesized that androgens depletion enables androgen-independent cells to proliferate and recolonize the tumor. Objectives: Natural bioactive compounds from edible plants and herbal remedies might potentially address this need. This review compiles the available cheminformatics-based studies and the translational studies regarding the use of natural products to manage CRPC. Methods: PubMed and Google Scholar searches for preclinical studies were performed, while ClinicalTrials.gov and PubMed were searched for clinical updates. Studies that were not in English and not available as full text were excluded. The period of literature covered was from 1985 to the present. Results and Conclusion: Our analysis suggested that natural compounds exert beneficial effects due to their broad-spectrum molecular disease-associated targets. In vitro and in vivo studies revealed several bioactive compounds, including rutaecarpine, berberine, curcumin, other flavonoids, pentacyclic triterpenoids, and steroid-based phytochemicals. Molecular modeling tools, including machine and deep learning, have made the analysis more comprehensive. Preclinical and clinical studies on resveratrol, soy isoflavone, lycopene, quercetin, and gossypol have further validated the translational potential of the natural products in the management of prostate cancer.

Identification of kinase inhibitors that rule out the CYP27B1-mediated activation of vitamin D: an integrated machine learning and structure-based drug designing approach

CYP27B1, a cytochrome P450-containing hydroxylase enzyme, converts vitamin D precursor calcidiol (25-hydroxycholecalciferol) to its active form calcitriol (1α,25(OH)₂D₃). Tyrosine kinase inhibitor such as imatinib is reported to interfere with the activation of vitamin D₃ by inhibiting CYP27B1 enzyme. Consequently, there is a decrease in the serum levels of active vitamin D that in turn may increase the relapse risk among the cancer patients treated with imatinib. Within this framework, the current study focuses on identifying other possible kinase inhibitors that may affect the calcitriol level in the body by inhibiting CYP27B1. To achieve this, we explored multiple machine learning approaches including support vector machine (SVM), random forest (RF), and artificial neural network (ANN) to identify possible CYP27B1 inhibitors from a pool of kinase inhibitors database. The most reliable classification model was obtained from the SVM approach with Matthews correlation coefficient of 0.82 for the external test set. This model was further employed for the virtual screening of kinase inhibitors from the binding database (DB), which tend to interfere with the CYP27B1-mediated activation of vitamin D. This screening yielded around 4646 kinase inhibitors that were further subjected to structure-based analyses using the homology model of CYP27B1, as the 3D structure of CYP27B1 complexed with heme was not available. Overall, five kinase inhibitors including two well-known drugs, i.e., AT7867 (Compound-2) and amitriptyline N-oxide (Compound-3), were found to interact with CYP27B1 in such a way that may preclude the conversion of vitamin D to its active form and hence testify the impairment of vitamin D activation pathway.